1. Repositório Aberto da Universidade do Porto
2. FEUP - Faculdade de Engenharia
3. FEUP - Dissertação

Author(s):	Rodrigo Gonçalves de Morais
Title:	CONGRATS - Convolutional Networks in GPU-based Reliability Assessment of Transmission Systems
Issue Date:	2021-07-19
Description:	Monte Carlo Simulation (MCS) is a powerful method frequently used for composite power system adequacy assessment. However it requires a considerable amount of time to provide accurate estimates for the reliability indexes. In the last years, mathematical approaches have been developed, for instance variance reduction techniques, with the aim to speed up this process. More recently, the MCS method has been implemented in parallel using a Graphics Processing Unit (GPU) to take advantage of the fast calculations provided by these computing platforms, resulting in reduction of the simulation time. In this dissertation, a new approach is developed to shrink simulation time by apllying Convolutional Neural Networks (CNN), trained on a GPU.
Subject:	Engenharia electrotécnica, electrónica e informática Electrical engineering, Electronic engineering, Information engineering
Scientific areas:	Ciências da engenharia e tecnologias::Engenharia electrotécnica, electrónica e informática Engineering and technology::Electrical engineering, Electronic engineering, Information engineering
DOI:	10.34626/w9g9-2w10
TID identifier:	202825159
URI:	https://hdl.handle.net/10216/135306
Document Type:	Dissertação
Rights:	openAccess
Appears in Collections:	FEUP - Dissertação

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.